Unsupervised Opinion Summarization as Copycat-Review Generation

@inproceedings{Brazinskas2020UnsupervisedOS,
  title={Unsupervised Opinion Summarization as Copycat-Review Generation},
  author={Arthur Brazinskas and Mirella Lapata and Ivan Titov},
  booktitle={ACL},
  year={2020}
}
Opinion summarization is the task of automatically creating summaries that reflect subjective information expressed in multiple documents, such as product reviews. While the majority of previous work has focused on the extractive setting, i.e., selecting fragments from input reviews to produce a summary, we let the model generate novel sentences and hence produce abstractive summaries. Recent progress in summarization has seen the development of supervised models which rely on large quantities… Expand
Few-Shot Learning for Abstractive Multi-Document Opinion Summarization
TLDR
This work shows that even a handful of summaries is sufficient to bootstrap generation of the summary text with all expected properties, such as writing style, informativeness, fluency, and sentiment preservation. Expand
Unsupervised Opinion Summarization with Noising and Denoising
TLDR
This paper enables the use of supervised learning for the setting where there are only documents available without ground truth summaries, and introduces several linguistically motivated noise generation functions and a summarization model which learns to denoise the input and generate the original review. Expand
Comparative Opinion Summarization via Collaborative Decoding
TLDR
A comparative summarization framework COCOSUM is developed, which consists of two few-shot summarization models that are jointly used to generate contrastive and common summaries. Expand
Unsupervised Opinion Summarization with Content Planning
TLDR
This work shows that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. Expand
PASS: Perturb-and-Select Summarizer for Product Reviews
TLDR
A key component of the PASS system relies on applying systematic perturbations to the model’s input during inference, which allows it to generate multiple different summaries per product, and develops a method for ranking these summaries according to desired criteria, enabling the system to almost entirely avoid the problem of selfcontradiction. Expand
Unsupervised Class-Specific Abstractive Summarization of Customer Reviews
Large-scale unsupervised abstractive summarization is sorely needed to automatically scan millions of customer reviews in today’s fast-paced e-commerce landscape. We address a key challenge inExpand
Learning Opinion Summarizers by Selecting Informative Reviews
TLDR
The task is formulated as jointly learning to select informative subsets of reviews and summarizing the opinions expressed in these subsets, with the importance of selecting informative reviews resulting in improved quality of summaries and reduced hallucinations. Expand
Aspect-Controllable Opinion Summarization
TLDR
This paper proposes an approach that allows the generation of customized summaries based on aspect queries and shows that the model outperforms the previous state of the art and generates personalized summaries by controlling the number of aspects discussed in them. Expand
Weakly-Supervised Opinion Summarization by Leveraging External Information
TLDR
This work proposes AspMem, a generative method that contains an array of memory cells to store aspect-related knowledge that can help obtain a better opinion representation and infer the aspect information more precisely. Expand
OpinionDigest: A Simple Framework for Opinion Summarization
TLDR
OpinionDigest, an abstractive opinion summarization framework, which uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 50 REFERENCES
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
TLDR
This work considers the setting where there are only documents with no summaries provided, and proposes an end-to-end, neural model architecture to perform unsupervised abstractive summarization, and shows that the generated summaries are highly abstractive, fluent, relevant, and representative of the average sentiment of the input reviews. Expand
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
TLDR
This paper focuses on the end-to-end abstractive summarization of a single product review without supervision, and learns the latent discourse tree without an external parser and generates a concise summary. Expand
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
TLDR
An opinion summarization dataset is introduced that includes a training set of product reviews from six diverse domains and human-annotated development and test sets with gold standard aspect annotations, salience labels, and opinion summaries. Expand
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
TLDR
A novel approach to unsupervised sentence summarization is proposed by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, the approach seeks a compressed sentence that can best predict the next sentence. Expand
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
TLDR
This paper evaluates summaries produced by state-of-the-art models via crowdsourcing and shows that such errors occur frequently, in particular with more abstractive models, which leads to an interesting downstream application for entailment models. Expand
Abstractive Summarization of Product Reviews Using Discourse Structure
TLDR
Quantitative and qualitative analysis of the results, based on two user studies, show that the approach significantly outperforms extractive and abstractive baselines. Expand
A Neural Attention Model for Abstractive Sentence Summarization
TLDR
This work proposes a fully data-driven approach to abstractive sentence summarization by utilizing a local attention-based model that generates each word of the summary conditioned on the input sentence. Expand
Extractive Summarization Using Multi-Task Learning with Document Classification
TLDR
A general framework for summarization that extracts sentences from a document using externally related information that is addressed in the framework of multi-task learning using curriculum learning for sentence extraction and document classification is proposed. Expand
A Deep Reinforced Model for Abstractive Summarization
TLDR
A neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL) that produces higher quality summaries. Expand
Generating Wikipedia by Summarizing Long Sequences
TLDR
It is shown that generating English Wikipedia articles can be approached as a multi- document summarization of source documents and a neural abstractive model is introduced, which can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. Expand
...
1
2
3
4
5
...